store_memento · MCP Memento MCP: Risk & Policy

WHAT IT DOES

What store_memento does on MCP Memento

AI agents use store_memento to create or update resources in MCP Memento — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP Memento environment.

WHY IT NEEDS A POLICY

Why store_memento needs a policy

'store_memento' most likely creates or saves a new memory/knowledge entry in the persistent store, which is a Write operation. The description is empty, so confidence is reduced, but the server context and naming convention strongly imply creating/writing data rather than reading or executing. It is reversible (sibling tool 'delete_memento' exists), so Destructive is not applicable.

From the tool's definition Tool name 'store_memento' on a server described as enabling 'storing and recalling solutions, facts, and decisions' — sibling tools include delete_memento, create_memento_relationship, boost/adjust confidence tools.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

store_memento Rate-limited

store_memento stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "store_memento": {
      "limits": [
        {
          "counter": "store_memento_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches MCP Memento, so you can run agents against it safely.

FAQ

Questions about store_memento

What does the store_memento tool do? +

store_memento. It is categorised as a Write tool in the MCP Memento MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on store_memento? +

Register the MCP Memento MCP server in PolicyLayer and add a rule for store_memento: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches MCP Memento. Nothing to install.

What risk level is store_memento? +

store_memento is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit store_memento? +

Yes. Add a rate_limit block to the store_memento rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block store_memento completely? +

Set action: deny in the PolicyLayer policy for store_memento. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides store_memento? +

store_memento is provided by the MCP Memento MCP server (x-hannibal/mcp-memento). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.